50 Steps to Master #AgenticAI in 2025-26
by @ingliguori #LLM #GenerativeAI #ArtificialIntelligence #MachineLearning
GENERATIVE AI
-
50 Steps to Master AgenticAI in 2025-26
By
–
-
Google launches AI video and music creation on Android phones
By
–
Your Android phone can now generate videos and music with AI. Google just launched: Gemini Omni → create and edit videos through conversation Lyria 3 → generate original songs from a prompt or photo The biggest shift? Creative tools that once required specialized
-
AI ARR triples to $500M, Firefly reaches $300M
By
–
Their AI-focused ARR tripled year over year to surpass $500 million. Very few enterprise software companies report this level of direct, paid AI adoption. The engine of this breakthrough is Firefly, which now reaches $300 million.
-
Sakana Fugu uses multi-agent orchestration of LLMs recursively
By
–
How does it work? Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackle complex, multi-step tasks. As shown in this figure, Fugu is a multi-agent
-
Question on DiffusionGemma’s transparency and hidden reasoning
By
–
What is the transparency of DiffusionGemma? Given how diffusion language models (Diffusion LMs) denoise tokens instead of generating them left to right, there is a concern about how reasoning will be hidden in
-
LLMs prove reasoning can emerge from language statistics
By
–
I am not garymarcusing here. LLMs are proof that it is possible to distill intelligent reasoning behavior by doing statistics over human language patterns
-
Using GLM 5.2 in Cursor with MagicPath setup guide
By
–
I’ve been using GLM 5.2 in Cursor with MagicPath and really like it so far.
— Pietro Schirano (@skirano) 21 juin 2026
Cursor Settings → Models:
Add your Fireworks key under “OpenAI API Key” and enable it
Base URL: https://t.co/2Bgawq3FJM
Model: accounts/fireworks/models/glm-5p2
Restart Cursor. Done. pic.twitter.com/fHpmqljQXdI’ve been using GLM 5.2 in Cursor with MagicPath and really like it so far. Cursor Settings → Models:
Add your Fireworks key under “OpenAI API Key” and enable it
Base URL: https://
api.fireworks.ai/inference/v1
Model: accounts/fireworks/models/glm-5p2 Restart Cursor. Done. -
Ollama slower, slop, code thieves; better alternatives listed
By
–
ollama > slower than llama.cpp on windows
> slower than mlx on mac
> slop useless wrapper
> literal code thieves alternatives? > lmstudio
> llama.cpp
> exllamav2/v3
> vllm
> sglang
> trt-llm literally anythingʼs better than ollama -
Why focus on inference engines: performance gains with vLLM and Sglang
By
–
Why do I focus on Inference Engines/Software Stacks for your hardware? – 2x RTX 3090s: ~14.5 tok/s → ~64 tok/s moving to vLLM w/ TP=2 – RTX PRO 6000: ~32 tok/s → ~110 tok/s moving to Sglang So: – CUDA/2+ GPUs: ExLlamaV3/vLLM/Sglang > llama.cpp – Edge: llama.cpp > Ollama